The Agent Skills Directory

[PROMPT_INJECTION]: No prompt injection patterns, role-play overrides, or instructions to bypass safety guidelines were detected in the skill instructions or reference material.
[DATA_EXFILTRATION]: No sensitive file access, hardcoded credentials, or unauthorized network operations were identified. The skill focuses on client-side performance metrics.
[OBFUSCATION]: The content is provided in plain text and standard Markdown. No base64 encoding, zero-width characters, or homoglyph substitutions were found.
[EXTERNAL_DOWNLOADS]: The skill references established documentation from trusted or well-known sources including frontendchecklist.io, web.dev, and developers.google.com. No automated remote code execution or suspicious downloads are present.
[REMOTE_CODE_EXECUTION]: There are no patterns of piping remote scripts to shells or dynamic execution of untrusted code. Code examples provided are for illustrative purposes for React and HTML developers.
[COMMAND_EXECUTION]: No dangerous system commands, privilege escalation (sudo), or persistence mechanisms (cron/bashrc) are included.
[INDIRECT_PROMPT_INJECTION]: While the skill involves auditing code and performance data, it does not ingest untrusted data in a way that exposes the agent to execution risks. It follows best practices for manual and automated auditing.

dom-size